ResearchTasksMulti-agent system security evaluationMulti-agent system security evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOWL (test)Crescendo0ASR2Feb 26, 2026LANGMANUS (test)Crescendo0ASR2Feb 26, 2026MAGENTIC-ONE (test)Crescendo0ASR2Feb 26, 2026